Research map / Detection and segmentation / 3D detection and driving
Multi-Level Fusion Based 3D Object Detection From Monocular Images
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add feature fusion between Fmax and Fmean (ablation) | Multi-Level Fusion 3D detector · KITTI val1, moderate, IoU=0.7 | AP3D: 2.88 -> 4.57 | Helped |
| Add feature fusion between Fmax and Fmean (ablation) | Multi-Level Fusion 3D detector · KITTI val2, moderate, IoU=0.7 | AP3D: 3.44 -> 4.84 | Helped |
| Add front-view feature-map input fusion after feature fusion (ablation) | Multi-Level Fusion 3D detector · KITTI val1, moderate, IoU=0.7 | AP3D: 4.57 -> 5.69 | Helped |
| Add front-view feature-map input fusion after feature fusion (ablation) | Multi-Level Fusion 3D detector · KITTI val2, moderate, IoU=0.7 | AP3D: 4.84 -> 5.39 | Helped |
| Replace MonoDepth disparity with stereo DispNet disparity (ablation) | Multi-Level Fusion 3D detector · KITTI val1, moderate, IoU=0.7 | 3D AP: 5.69 -> 9.80 | Helped |
| Replace MonoDepth disparity with stereo DispNet disparity (ablation) | Multi-Level Fusion 3D detector · KITTI val1, moderate, IoU=0.5 | 3D AP: 29.48 -> 47.42 | Helped |
| Replace MonoDepth disparity with stereo DispNet disparity (ablation) | Multi-Level Fusion 3D detector · KITTI val1, moderate, IoU=0.7 | Bird's eye view AP: 13.63 -> 19.54 | Helped |
| Replace MonoDepth disparity with stereo DispNet disparity (ablation) | Multi-Level Fusion 3D detector · KITTI val1, moderate, IoU=0.5 | Bird's eye view AP: 36.73 -> 53.65 | Helped |
Closest papers by meaning
- Triangulation Learning Network: From Monocular to Stereo 3D Object Detection (CVPR 2019 · similarity 0.91)
- Learning Depth-Guided Convolutions for Monocular 3D Object Detection (CVPR 2020 · similarity 0.90)
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.88)
- FD3D: Exploiting Foreground Depth Map for Feature-Supervised Monocular 3D Object Detection (AAAI 2024 · similarity 0.88)
- MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders (NeurIPS 2024 · similarity 0.88)
- MonoCD: Monocular 3D Object Detection with Complementary Depths (CVPR 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.